Hugging Face Trending Papers

When Do Fewer Visual Tokens Accelerate Multimodal Inference? A Break-Even Study Across Decision Locations and Hardware

Read the original on Hugging Face Trending Papers →

Fewer visual tokens do not guarantee lower end-to-end latency. We evaluate break-even with a reproducible protocol that accounts for decision overhead, shared work, and the operators each policy can avoid.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Aug 11

Not All Visual Tokens Are Equally Safe to Remove:Consequence-Sensitive Visual Token Compression

arXiv:2608. 09176v1 Announce Type: cross Abstract: Visual token compression for vision--language models (VLMs) has largely relied on criteria such as attention, redundancy, and uncertainty to maximize average accuracy under a fixed compute budget, implicitly assuming that all errors carry equal cost.

By Jingbo Wen, Liang He, Mingyu Cao, Haoyu Wang, Minxuan Hu, Kangning Cui, Xilu Wang